Engineering and Computer Science at M.I.T. and a member of the Artificial Intelligence Laboratory where he leads the mobile robot group. He has authored two books, numerous scientific papers, and is the editor of the International Journal of Computer Vision. There is an alternative route to Artificial Intelligence that diverges from the directions pursued under that banner for the last thirty some years. The traditional approach has emphasized the abstract manipulation of symbols, whose grounding, in physical reality has. rarely been achieved. We explore a research methodology which emphasizes ongoing physical interaction with the environment as the primary source of constraint on the design of intelligent systems. We show how this methodology has recently had significant successes on a par with the most successful classical efforts. We outline plausible future work along these lines which can lead to vastly more ambitious systems. 1.

We describe a project to capitalize on newly available levels of computational resources in order to understand human cognition. We are building an integrated physical system including vision, sound input and output, and dextrous manipulation, all controlled by a continuously operating large scale parallel MIMD computer. The resulting system will learn to "think " by building on its bodily experiences to accomplish progressively more abstract tasks. Past experience suggests that in attempting to build such an integrated system we will have to fundamentally change the way artificial intelligence, cognitive science, linguistics, and philosophy think about the organization of intelligence. We expect to be able to better reconcile the theories that will be developed with current work in neuroscience.

In recent years there has been a move within the artificial intelligence and robotics communities towards building complete autonomous creatures that operate in the physical world. Certain approaches have proven quite successful, and have caused a re-analysis within the field of artificial intelligence of what components are necessary in the intellectual architecture of such creatures. However nothing built thus far yet comes close the dreams that many people hold dearly. Furthermore there has been quite some criticism of the new approaches for lacking adequate theoretical justification. In this paper we outline some of the more obvious challenges that remain for these new approaches, and suggest new ways of thinking about the tasks ahead, in order to decompose the field into a number of manageable sub-areas that can be used to shape further research. 1 Introduction There is a growing interest in building artificial creatures of some sort. One example is the recent boom in a field kn...

Good Old Fashioned Artificial Intelligence and Robotics (GOFAIR) relies on a set of restrictive Omniscient Fortune Teller Assumptions about the agent, the world and their relationship. The emerging Situated Agent paradigm is challenging GOFAIR by grounding the agent in space and time, relaxing some of those assumptions, proposing new architectures and integrating perception, reasoning and action in behavioral modules. GOFAIR is typically forced to adopt a hybrid architecture for integrating signal-based and symbol-based approaches because of the inherent mismatch between the corresponding on-line and off-line computational models. It is argued that Situated Agents should be designed using a unitary on-line computational model. The Constraint Net model of Zhang and Mackworth satisfies that requirement. Two systems for situated perception built in our laboratory are described to illustrate the new approach: one for visual monitoring of a robot's arm, the other for real-time visual control of multiple robots competing and cooperating in a dynamic world.

Methods for designing and building perceptual agents should be clean, powerful and practical. But no methodology satisfies all three criteria, yet. Our methodologies are evolving dialectically. The symbolic methods of Good Old-Fashioned Artificial Intelligence and Robotics (GOFAIR) constitute the original thesis. The antithesis is reactive Insect AI. The emerging synthesis, Situated Agents, needs formal rigor and practical tools. A robot is a hybrid intelligent dynamical system, consisting of a controller coupled to its body. The Constraint Net (CN) model of Zhang and Mackworth is a unitary framework for building hybrid intelligent systems as situated agents. Most other robot design methodologies use hybrid models of hybrid systems, awkwardly combining offline computational models of high-level perception, reasoning and planning with online models of low-level sensing and control. In CN, the designer specifies the robot's vision, control and motor systems uniformly as online systems. T...

Knowledge-based vision for robots needs a radi-cally new approach. The traditional approach has not made substantial progress for various reasons including the engineering problems of building sys-tems based on a hybrid on-line/off-line paradigm. A new situated agent approach is presented. The Constraint Net model of Zhang and Mackworth allows the designer to specify the robot’s vision, control and motor systems uniformly as on-line systems. If the perceptual and control systems are designed as constraint-satisfying devices then the total robotic system, consisting of the robot symmetrically coupled to the environment, can be proven correct. Examples of this approach are given. 1.